Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    퇴
    -0.07
    Deadline
    -0.07
    issippi
    -0.06
    isify
    -0.06
    足足
    -0.06
    cmc
    -0.06
    agenta
    -0.06
    inces
    -0.06
    深深的
    -0.06
     ربما
    -0.06
    POSITIVE LOGITS
    stor
    0.07
    usto
    0.07
    峒
    0.06
     ổ
    0.06
    larınd
    0.06
    瑭
    0.06
     Activity
    0.06
    zioni
    0.06
     жизни
    0.06
     Dar
    0.06
    Act Density 0.000%

    No Known Activations